RRadixark
Every Radixark model UltraGPT can reach, kept in sync with the live catalog — pricing, context window and capabilities for each one.
1 model from Radixark Up to 262.1K tokens of context
1
Models tracked
1
Providers
1
Reasoning models
1
See images (vision)
262K
Largest context window
0
Free to run
All Radixark models.
Search and filter this provider's lineup — pricing per million tokens, context window, modalities, reasoning effort and independent benchmark scores where available.
1 of 1 models
DaisyRose 27B is an open-weight multimodal reasoning model from RadixArk, trained from Qwen3.8 27B using reinforcement learning only on long-horizon agent tasks, with no supervised fine-tuning or distillation. It is...
ReasoningTool callingVisionStreamingJSON mode
Context window262.1K tok
Max output235.9K tok
ReleasedNov 21, 2026
Knowledge cutoff—
Text + ImageText
Input$0.15 / 1M tok
Output$1.88 / 1M tok
Cache read$0.037 / 1M tok
Effort: xhigh, medium, low, none
